paper-with-me

홈 › Papers

Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition

2022-07-27 · Tomoya Nitta, Tsubasa Hirakawa, Hironobu Fujiyoshi, Toru Tamaki

In this paper we propose an extension of the Attention Branch Network (ABN) by using instance segmentation for generating sharper attention maps for action recognition. Methods for visual explanation such as Grad-CAM usually generate blurry maps which are not intuitive for humans to understand, particularly in recognizing actions of people in videos. Our proposed method, Object-ABN, tackles this issue by introducing a new mask loss that makes the generated attention maps close to the instance segmentation result. Further the PC loss and multiple attention maps are introduced to enhance the sharpness of the maps and improve the performance of classification. Experimental results with UCF101 and SSv2 shows that the generated maps by the proposed method are much clearer qualitatively and quantitatively than those of the original ABN.

📄 PDF Abstract BibTeX arXiv:2207.13306

Code (0)

등록된 구현이 없습니다.

Tasks

Action RecognitionInstance SegmentationSegmentationSemantic Segmentation

Methods 이 논문이 사용한 방법론

pc 설명 없음

Similar Papers 제목 키워드 기반

Inhibited Self-Attention: Sharpening Focus in Vision Transformers

2026-07-14 · Peter R. D. van der Wal, Nicola Strisciuglio, George Azzopardi arxiv

Vision Transformers (ViTs) have demonstrated remarkable performance in computer vision tasks. However, their self-attention mechanism often diffuses focus across background regions, relying on spurious correlations rathe…

Sharp Attention Network via Adaptive Sampling for Person Re-identification

2018-05-07 · Chen Shen, Guo-Jun Qi, Rongxin Jiang, Zhongming Jin 외

In this paper, we present novel sharp attention networks by adaptively sampling feature maps from convolutional neural networks (CNNs) for person re-identification (re-ID) problem. Due to the introduction of sampling-bas…

Person Re-Identification

Learned Local Attention Maps for Synthesising Vessel Segmentations

2023-08-24 · Yash Deo, Rodrigo Bonazzola, Haoran Dou, Yan Xia 외

Magnetic resonance angiography (MRA) is an imaging modality for visualising blood vessels. It is useful for several diagnostic applications and for assessing the risk of adverse events such as haemorrhagic stroke (result…

DecoderDiagnostic

DFNet: Discriminative feature extraction and integration network for salient object detection

2020-04-03 · Mehrdad Noori, Sina Mohammadi, Sina Ghofrani Majelan, Ali Bahri 외

Despite the powerful feature extraction capability of Convolutional Neural Networks, there are still some challenges in saliency detection. In this paper, we focus on two aspects of challenges: i) Since salient objects a…

object-detectionObject DetectionRGB Salient Object DetectionSaliency Detection+1

Towards Reducing Severe Defocus Spread Effects for Multi-Focus Image Fusion via an Optimization Based Strategy

2020-12-29 · Shuang Xu, Lizhen Ji, Zhe Wang, Pengfei Li 외

Multi-focus image fusion (MFF) is a popular technique to generate an all-in-focus image, where all objects in the scene are sharp. However, existing methods pay little attention to defocus spread effects of the real-worl…

Multi Focus Image FusionSSIM